DALLE-URBAN: Capturing the urban design expertise of large text to image transformers

Seneviratne, Sachith; Senanayake, Damith; Rasnayaka, Sanka; Vidanaarachchi, Rajith; Thompson, Jason

doi:10.1109/dicta56598.2022.10034603

Cited by 12 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This application of Generative AI in this context is in its infancy with some early work conducted by Wijnands et al (2019). Seneviratne et al (2022) already demonstrated how image generation models in their base-trained state can generate convincing and representative urban planning concepts. Nevertheless, more investigation is needed, not only into the technology but also its responsible use (Saetra, 2023).…”

Section: Discussion and The Way Forwardmentioning

confidence: 99%

“…With the rise of visualisation methods, LLMs present a unique opportunity to increase communication pathways through better NBS planning visualisation, and the generation of new ideas. The emerging field of 'Generative AI', encompassing LLMs, generative adversarial networks (GANs), variational autoencoders (VAEs) and diffusion models can also yield photo-realistic representations of the urban environment that can be changed through preselected prompts to the model (e.g., Wijnands et al, 2019;Seneviratne et al, 2022). This can enable smoother communication throughout the planning process (Wijnands et al, 2019), but also allow communication of results to the broader public, aiming at informing and educating.…”

Section: Discussion and The Way Forwardmentioning

confidence: 99%

See 1 more Smart Citation

Urban nature-based solutions planning for biodiversity outcomes: human, ecological, and artificial intelligence perspectives

Prodanovic,

Bach,

Stojkovic

2024

Urban Ecosyst

View full text Add to dashboard Cite

Nature-based solutions (NBS) harness ecosystem services for urban enhancement, promoting biodiversity, habitat creation, and water management while improving human well-being. However, decision-making often favours specific NBS designs, leading to uneven benefits distribution. Whereas human-centric NBS design relies on convenience, financial sustainability, historical aspects, and amenity increase through NBS technical solutions, flora- and fauna-centric (or eco-centric) design targets spatial connectedness of blue-green spaces, increase in species richness, and habitat within urban centres. Both approaches can shape the urban biodiversity landscape, yet; they often clash around planning priorities. Recent advances in AI offer potential for AI-centric urban planning, though its role remains unclear. This study examines the interplay between biodiversity and NBS planning across human-, eco-, and AI-centric domains, aiming for balanced urban outcomes. We blended narrative, integrative, and systematic literature review and propose future steps for more balanced NBS development. The findings of this work suggest that AI presents an opportunity for a more balanced NBS design through its applications in climate change prediction, water management, and project visualisation. Incorporating AI into urban planning tools can expedite modelling process, improve stakeholder communication, and enhance project outcomes visualisation. By integrating human, eco, and AI-centric approaches, urban planners can foster resilience and sustainability in NBS implementation, ensuring equitable distribution of benefits across urban landscapes.

show abstract

Section: Discussion and The Way Forwardmentioning

confidence: 99%

Section: Discussion and The Way Forwardmentioning

confidence: 99%

Urban nature-based solutions planning for biodiversity outcomes: human, ecological, and artificial intelligence perspectives

Prodanovic,

Bach,

Stojkovic

2024

Urban Ecosyst

View full text Add to dashboard Cite

show abstract

“…Research exists that uses AI text-to-image models for visualisation [24,25] and in landscape design [22,26]. Most of the recent scholarship, though, centres around evaluations of the quality and representation of images generated by different text-to-image models [25] or a specific text-to-image model by a human or a system with a human in the loop [27] using quantitative methods. To our knowledge, no research combines both aspects used in this paper that aim to fill that research gap by developing a qualitative approach for landscape visualisation that enables non-professionals without the relevant artistic skills to generate representative AI images.…”

Section: Recent Endeavours In Artificial Intelligence In Landscape Ar...mentioning

confidence: 99%

“…In their analysis of the capabilities of a text-to-image model, i.e., DALL.E 2 [50], for capturing the essence of urban environments, Seneviratne et al [27] introduced an approach for writing prompts that can generate representative images. They suggested four dimensions of urban environment representation: the image format domain, geography of generated images, urban quality, and urban unit of analysis.…”

Section: Ai-powered Visualisation Approachmentioning

confidence: 99%

Post-Conflict Urban Landscape Storytelling: Two Approaches to Contemporary Virtual Visualisation of Oral Narratives

Alkhateeb,

Storie,

Külvik

2024

Land

View full text Add to dashboard Cite

Armed conflicts and resulting displacement disrupt people’s sense of place, leading to an imbalance in the people–place relationship, exaggerated by rehabilitation efforts that overlook the sense of place among conflict- and displacement-impacted communities. A continuous landscape narrative that extends from pre- to post-conflict times contributes to recreating the essence of lost landscapes and therefore reconnecting their sense of place. Focusing on a Syrian city that hosted internally displaced persons (IDPs) in the aftermath of the Syrian conflict, this study aims to structure a virtual landscape and narrative depiction of conflict-impacted landscapes. This study proposes a storytelling approach for narrative construction and an AI-powered visualisation approach to revive the image of the elusive landscapes. This study utilised qualitative research methods through in-depth, semi-structured interviews for data collection and an online survey for exploring the perception of virtual landscape images generated with AI text-to-image models (DALL.E 2 and Bing Image Creator). This study indicates that narratives, supported by AI visualisation, are reliable for comprehending landscape transformation and changes in the sense of place. The two approaches can serve as rehabilitation initiatives in post-crisis settings to recall images of elusive landscapes to save them from being lost forever.

show abstract

“…Overall, the assessment revealed that 'text to image' AI models can satisfy the need of speeding up the design process of certain disciplines (such as graphic design and artistry), but for scientific design disciplines, such as urban planning and design, it indicated that further domain-specific research may be required. (Seneviratne et al, 2022). These findings highlight that existing AI concepts may not be fully applicable in architecture and its design procedure.…”

Section: Introductionmentioning

confidence: 97%

Designing Tomorrow: AI and the Future of Architectural Design Process

Tellios,

Koulali,

Valsamidou

2023

FORUM A+P

View full text Add to dashboard Cite

This essay explores the transformative role of Artificial Intelligence (AI) in the field of architecture, focusing on the impact on design innovation, production processes, as well as the ethical implications arising from inherent biases within these technologies. As AI becomes increasingly integrated into architectural practices, it offers the potential to revolutionize the discipline by enhancing efficiency, creativity, and sustainability. This investigation delves into the history and evolution of AI in architecture, tracing their journey from early computational design experiments to their current applications in generative design and robotic construction, which exemplify the shift towards more innovative and sustainable architectural practices. Furthermore, the essay highlights the involvement of the INNEN research team in integrating AI into academic and research activities within and besides the curriculum. It delves into the ways in which AI technologies are reshaping the boundaries of architectural design and construction, emphasizing on practical applications of AI in architectural design in education and professional work. This analysis uncovers the profound possibilities of AI in formulating groundbreaking design approaches and construction methods, underscoring research's role in propelling architectural thinking and practice forward through the use of technology.

show abstract

DALLE-URBAN: Capturing the urban design expertise of large text to image transformers

Cited by 12 publications

References 19 publications

Urban nature-based solutions planning for biodiversity outcomes: human, ecological, and artificial intelligence perspectives

Urban nature-based solutions planning for biodiversity outcomes: human, ecological, and artificial intelligence perspectives

Post-Conflict Urban Landscape Storytelling: Two Approaches to Contemporary Virtual Visualisation of Oral Narratives

Designing Tomorrow: AI and the Future of Architectural Design Process

Contact Info

Product

Resources

About